> ## Documentation Index
> Fetch the complete documentation index at: https://docs.fincept.in/llms.txt
> Use this file to discover all available pages before exploring further.

# Distributions, copulas and stress tests

> Fitted return distributions per asset (normal, Student t, Johnson SU, normal inverse Gaussian, best by AIC/BIC) with quantiles and Q-Q numbers, bivariate copulas (Gaussian, Student t, Clayton, Gumbel, Joe, independent, rotations) with tail dependence, regular vine copulas, synthetic scenario generation and conditional stress tests of a portfolio.

Toolset `pflab_distributions`: 4 tools.

| Tool | What it does | Notes |
| - | - | - |
| `pflab_univariate_distribution` | Fits each asset's returns to a normal, Student t, Johnson SU or normal inverse Gaussian distribution, or selects the best by AIC/BIC. | |
| `pflab_bivariate_copula` | Fits a bivariate copula to two assets' pseudo-observations (ranks): Gaussian, Student t, Clayton, Gumbel or Joe with rotations, or the best by AIC/BIC with an independence test. | |
| `pflab_vine_copula` | Fits a regular vine copula: a marginal distribution per asset and a tree of pair copulas (Gaussian, Student t, Clayton, Gumbel, Joe, independent, with rotations) capturing non-Gaussian and tail dependence, then samples synthetic scenarios, optionally conditioned on some assets' returns. | |
| `pflab_stress_test` | Synthetic stress test: a vine copula fitted to the history is sampled conditionally on the stressed assets' returns, so every other asset moves consistently with the fitted (non-Gaussian, tail-dependent) structure. | |

Inputs, limits and outputs are described in [Fincept Portfolio Lab](/guides/fincept-portfolio-lab). Full schemas: `fincept_describe_tool`.


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.